CRAN Submission for 0.71.1 (#3311)

* fix for CRAN manual checks

* fix for CRAN manual checks

* pass local check

* fix variable naming style

* Adding Philip's record

CONTRIBUTORS.md

@@ -7,8 +7,8 @@ Committers
 Committers are people who have made substantial contribution to the project and granted write access to the project.
 * [Tianqi Chen](https://github.com/tqchen), University of Washington
   - Tianqi is a PhD working on large-scale machine learning, he is the creator of the project.
-* [Tong He](https://github.com/hetong007), Simon Fraser University
+* [Tong He](https://github.com/hetong007), Amazon AI
-  - Tong is a master student working on data mining, he is the maintainer of xgboost R package.
+  - Tong is an applied scientist in Amazon AI, he is the maintainer of xgboost R package.
 * [Vadim Khotilovich](https://github.com/khotilov)
   - Vadim contributes many improvements in R and core packages.
 * [Bing Xu](https://github.com/antinucleon)

Makefile

@@ -267,7 +267,7 @@ Rbuild: Rpack
 	rm -rf xgboost
 
 Rcheck: Rbuild
-	R CMD check  xgboost*.tar.gz
+	R CMD check xgboost*.tar.gz
 
 -include build/*.d
 -include build/*/*.d

R-package/DESCRIPTION

@@ -2,7 +2,7 @@ Package: xgboost
 Type: Package
 Title: Extreme Gradient Boosting
 Version: 0.71.1
-Date: 2018-04-11
+Date: 2018-05-11
 Authors@R: c(
   person("Tianqi", "Chen", role = c("aut"),
          email = "tianqi.tchen@gmail.com"),
@@ -14,7 +14,20 @@ Authors@R: c(
          email = "khotilovich@gmail.com"),
   person("Yuan", "Tang", role = c("aut"),
          email = "terrytangyuan@gmail.com",
-         comment = c(ORCID = "0000-0001-5243-233X"))
+         comment = c(ORCID = "0000-0001-5243-233X")),
+  person("Hyunsu", "Cho", role = c("aut"),
+         email = "chohyu01@cs.washington.edu"),
+  person("Kailong", "Chen", role = c("aut")),
+  person("Rory", "Mitchell", role = c("aut")),
+  person("Ignacio", "Cano", role = c("aut")),
+  person("Tianyi", "Zhou", role = c("aut")),
+  person("Mu", "Li", role = c("aut")),
+  person("Junyuan", "Xie", role = c("aut")),
+  person("Min", "Lin", role = c("aut")),
+  person("Yifeng", "Geng", role = c("aut")),
+  person("Yutian", "Li", role = c("aut")),
+  person("XGBoost contributors", role = c("cph"),
+         comment = "base XGBoost implementation")
   )
 Description: Extreme Gradient Boosting, which is an efficient implementation
     of the gradient boosting framework from Chen & Guestrin (2016) <doi:10.1145/2939672.2939785>.
@@ -28,6 +41,7 @@ Description: Extreme Gradient Boosting, which is an efficient implementation
 License: Apache License (== 2.0) | file LICENSE
 URL: https://github.com/dmlc/xgboost
 BugReports: https://github.com/dmlc/xgboost/issues
+NeedsCompilation: yes
 VignetteBuilder: knitr
 Suggests:
     knitr,

R-package/R/callbacks.R

@@ -691,11 +691,6 @@ cb.gblinear.history <- function(sparse=FALSE) {
 #' For an \code{xgb.cv} result, a list of such matrices is returned with the elements
 #' corresponding to CV folds.
 #'
-#' @examples
-#' \dontrun{
-#' See \code{\link{cv.gblinear.history}}
-#' }
-#'
 #' @export
 xgb.gblinear.history <- function(model, class_index = NULL) {
 

R-package/R/xgb.dump.R

@@ -30,7 +30,8 @@
 #' bst <- xgboost(data = train$data, label = train$label, max_depth = 2, 
 #'                eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
 #' # save the model in file 'xgb.model.dump'
-#' xgb.dump(bst, 'xgb.model.dump', with_stats = TRUE)
+#' dump_path = file.path(tempdir(), 'model.dump')
+#' xgb.dump(bst, dump_path, with_stats = TRUE)
 #' 
 #' # print the model without saving it to a file
 #' print(xgb.dump(bst, with_stats = TRUE))

R-package/demo/basic_walkthrough.R

@@ -99,7 +99,8 @@ err <- as.numeric(sum(as.integer(pred > 0.5) != label))/length(label)
 print(paste("test-error=", err))
 
 # You can dump the tree you learned using xgb.dump into a text file
-xgb.dump(bst, "dump.raw.txt", with_stats = T)
+dump_path = file.path(tempdir(), 'dump.raw.txt')
+xgb.dump(bst, dump_path, with_stats = T)
 
 # Finally, you can check which features are the most important.
 print("Most important features (look at column Gain):")

R-package/man/xgb.cv.Rd

@@ -99,7 +99,7 @@ An object of class \code{xgb.cv.synchronous} with the following elements:
   \item \code{params} parameters that were passed to the xgboost library. Note that it does not 
         capture parameters changed by the \code{\link{cb.reset.parameters}} callback.
   \item \code{callbacks} callback functions that were either automatically assigned or 
-        explicitely passed.
+        explicitly passed.
   \item \code{evaluation_log} evaluation history storead as a \code{data.table} with the
         first column corresponding to iteration number and the rest corresponding to the 
         CV-based evaluation means and standard deviations for the training and test CV-sets.

R-package/man/xgb.dump.Rd

@@ -44,7 +44,8 @@ test <- agaricus.test
 bst <- xgboost(data = train$data, label = train$label, max_depth = 2, 
                eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
 # save the model in file 'xgb.model.dump'
-xgb.dump(bst, 'xgb.model.dump', with_stats = TRUE)
+dump.path = file.path(tempdir(), 'model.dump')
+xgb.dump(bst, dump.path, with_stats = TRUE)
 
 # print the model without saving it to a file
 print(xgb.dump(bst, with_stats = TRUE))

R-package/man/xgb.gblinear.history.Rd

@@ -27,9 +27,3 @@ A helper function to extract the matrix of linear coefficients' history
 from a gblinear model created while using the \code{cb.gblinear.history()}
 callback.
 }
-\examples{
-\dontrun{
-See \\code{\\link{cv.gblinear.history}}
-}
-
-}

R-package/tests/testthat/test_helpers.R

@@ -42,9 +42,10 @@ mbst.GLM <- xgboost(data = as.matrix(iris[, -5]), label = mlabel, verbose = 0,
 
 test_that("xgb.dump works", {
   expect_length(xgb.dump(bst.Tree), 200)
-  expect_true(xgb.dump(bst.Tree, 'xgb.model.dump', with_stats = T))
+  dump_file = file.path(tempdir(), 'xgb.model.dump')
-  expect_true(file.exists('xgb.model.dump'))
+  expect_true(xgb.dump(bst.Tree, dump_file, with_stats = T))
-  expect_gt(file.size('xgb.model.dump'), 8000)
+  expect_true(file.exists(dump_file))
+  expect_gt(file.size(dump_file), 8000)
 
   # JSON format
   dmp <- xgb.dump(bst.Tree, dump_format = "json")